The Berkeley Phonetics Machine

Ronald L. Sprouse, Keith Johnson


The Berkeley Phonetics Machine is a Linux virtual machine image produced and used by the UC Berkeley Phonology Lab as a platform for phonetic research. It contains a full data analysis stack based on Python and R and also specialized tools for phonetic research. The machine is designed as a flexible and productive platform for established and novel research agendas that can be easily shared and reproduced. We list the software available in the machine, which includes many command-line tools for acoustic analysis and media file manipulation, as well as specialized Python libraries. We also discuss the use of this machine in the Phonology Lab and in phonetics courses. The overall experience with the machine has been positive, as faculty and graduate students are able to share and execute scripts in a common working environment. Undergraduate students have less opportunity to master the virtual machine environment but benefit from simplified instructions and fewer installation and operating problems. The primary difficulty that we have encountered has been with a few underpowered student computers that cannot run the virtual machine or do not run it well.


DOI: 10.21437/Interspeech.2016-524

Cite as

Sprouse, R.L., Johnson, K. (2016) The Berkeley Phonetics Machine. Proc. Interspeech 2016, 1623-1626.

Bibtex
@inproceedings{Sprouse+2016,
author={Ronald L. Sprouse and Keith Johnson},
title={The Berkeley Phonetics Machine},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-524},
url={http://dx.doi.org/10.21437/Interspeech.2016-524},
pages={1623--1626}
}